chargoddard's picture
Update README.md
2e738f1
|
raw
history blame
303 Bytes
metadata
license: apache-2.0
datasets:
  - togethercomputer/RedPajama-Data-1T-Sample
language:
  - en

This is another training run of SmolLlamix-8x101M with slightly different hyperparameters. Just testing to see how it holds up against the first run.